Skip to content
Get packs

LibreChat

Self-hosted, open-source chat interface for many AI models, with agents, tools, and multi-user login.

GitHub Download source
Stars
46.6k
Forks
9.6k
Licence
MIT
Language
TypeScript
Last update
4 days ago
Type
App

What it is

LibreChat is a free, open-source web app that looks like ChatGPT but lets you connect to many AI providers, such as OpenAI, Anthropic (Claude), Google, Azure, and local models through compatible APIs. You run it on your own server, so conversations and accounts stay under your control. It also includes agents, tool integrations via MCP, file handling, and code execution.

  • Chat with Claude, GPT, Gemini, or a local model from one interface
  • Build a custom agent with its own instructions, files, and tools
  • Run Python, JavaScript, or other supported languages in a sandboxed code interpreter
  • Connect external tools through Model Context Protocol (MCP) servers
  • Generate or edit images with supported image models

Great for

  • Teams that want one shared chat interface across several AI providers
  • People who want to self-host a ChatGPT-style interface and keep their data on their own server
  • Developers who want to connect custom OpenAI-compatible endpoints or local models
  • Organizations that need multi-user login and role-based access

Not ideal for

  • People who just want to chat with AI and do not want to run a server; a hosted service is simpler
  • Users with no hosting or Docker experience, since setup involves configuring a server and API keys
  • Those who need features the README marks as experimental, such as attached code workspaces, to be stable
Step-by-step guide: how to use LibreChatInstall, first run, examples, tips and FAQs
LibreChat alternativesLibreChat vs NextChatAnythingLLM vs LibreChatLibreChat vs MindsHubAI Website Cloner vs LibreChatLibreChat vs One APIChatbot UI vs LibreChatHermes WebUI vs LibreChatDeepWiki vs LibreChat

How to get it

  1. 1

    Clone and build from source

    You'll need: Git · Docker (the README's deploy options suggest Docker-based setup, unverified here)

    Clone the repository

    git clone https://github.com/LibreChat-AI/LibreChat
  2. 2

    Run it

    • Clone the repository and follow the setup instructions in its README and docs at docs.librechat.ai.
    • Configure your environment settings and API keys for the AI providers you want to use.
    • Start the application using the method the docs describe.
    • Open the local web address in your browser and log in or create an account.
    • Select a model or endpoint and send your first message.
  3. 3

    Get the most out of it

    • Use Custom Endpoints to connect any OpenAI-compatible API without a proxy
    • Create reusable Presets to save model settings and switch mid-chat
    • Add MCP servers to give agents access to external tools
    • Use Skills (SKILL.md bundles) to package reusable agent instructions
    • Use Fork and branching to explore alternative conversation paths

Downloads

Source code (.zip)main branch · straight from GitHubOfficial website & docslibrechat.ai/

Strengths

  • Supports many AI providers and any OpenAI-compatible API in one interface
  • Open source under the MIT license and self-hostable
  • Has a large user base, with over 46,000 GitHub stars

Trade-offs

  • Self-hosting requires technical setup and ongoing maintenance
  • Some newer features, such as attached workspaces, are labeled highly experimental
  • The README is truncated here, so detailed install steps could not be verified from this excerpt

How it compares

ProjectStarsTypeLevelUpdatedBest for
LibreChat (this)46.6kAppintermediate4 days agoTeams that want one shared chat interface across several AI providers
chatbot-ui33.3kAppintermediate2.3 years agoDevelopers who want a self-hosted chat interface for OpenAI or Azure OpenAI models
anything-llm67.8kAppbeginner6 days agoPeople who want a private ChatGPT-style assistant over their own PDFs and text files
watermarks-remover25.9kAI model / agentintermediate4 days agoDevelopers who use AI coding agents and want written files scrubbed of provenance metadata
one-api37.3kAppintermediate10 months agoDevelopers who want one OpenAI-compatible endpoint for several model providers
langchain149kFrameworkintermediate4 days agoPython developers building LLM-powered applications

Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.